What’s new in Dataiku
Build AI value faster with a governed catalog of reusable building blocks, agent-generated artifacts, and more in Dataiku 15.1.
Cobuild: Go from business needs to enterprise AI projects
Describe what you want in plain language. Cobuild generates the right end-to-end AI project in Dataiku — data pipelines, machine learning models, agents, and applications.
Everything is delivered as a visual flow that teams can inspect, edit, and approve, so speed doesn’t come at the cost of control.
Start from trusted building blocks with the Dataiku Catalog
The expanded Dataiku Catalog puts agents, tools, models, skills, data, and more in one governed place.
Find trusted assets in plain language, and let Cobuild build from them so new projects start from something proven.
Turn agent conversations into finished deliverables
Agents in Agent Hub now generate documents as the conversation unfolds. Preview them in the new Artifacts Panel and refine them just by chatting.
Download the result as DOCX, PPTX, or PDF, grounded in your data and enterprise logic.
Build trusted AI from your favorite coding agent
Dataiku Headless brings Cobuild into the agentic coding tools your teams use every day, like Claude Code, Codex, Cursor, and Snowflake CoCo.
Build Dataiku projects, migrate work created elsewhere, and handle admin tasks without switching context, all within Dataiku’s governance.
Test semantic models before they reach production
Define sets of real business questions with expected SQL and answers, then run them against a semantic model to measure cost, latency, and accuracy.
Built-in diagnosis shows exactly what to fix, so teams improve model quality faster and ship agents they can trust.
Easily debug your agents visually
Understand what your agent is doing at every step with a visual, streamed view of execution. See what it calls and what inputs and outputs shape the outcome.
The debug mode lets users visually inspect the steps of their agent while they run so teams can iterate faster and deploy with fewer surprises.
Explore previous Dataiku releases
Explore Dataiku 15.1
New features include the extended Catalog, Agent Hub Artifacts, Dataiku Headless, semantic model testing, and more.
Detailed release in a box deckExplore Dataiku 15.0
New features include Agent Skills, agent live debugging, native MCP capabilities, multi-turn conversation API, LLM Provider native web search, and more.
Detailed release in a box deckExplore Dataiku 14.6
New features include Dataiku Agents on Microsoft Teams, native SharePoint document support, Snowflake Semantic Views import, and the RFx Accelerator business application.
Detailed release in a box deckExplore Dataiku 14.5
New features include Agent Chat, Extract Fields recipe, Process Mining application, code agents and webapp testing & debugging in Code Studios, and Claude Code in Code Studios.
Detailed release in a box deckExplore Dataiku 14.4
New features include Structured Visual Agent & Human Approval, Agent Review, Semantic Models for Agents, Interact with agent on Slack, Flow Assistant, & AI Search.
Detailed release in a box deckExplore Dataiku 14.3
New features include Agent Evaluation, Agent Diagram, and Agent Hub enhancements.
Detailed release in a box deckExplore Dataiku 14.2
New features include Agent Hub, connect agents to tools like Gmail, Jira, or Slack, Governance Policies and AI Portfolio Badges.
Detailed release in a box deckExplore Dataiku 14.1
New features include Ask Dataiku, Project Standards, and a streamlined Agent Testing interface.
Detailed release in a box deckExplore Dataiku 14.0
New features include a new Dataiku homepage, Python tools for Visual Agents, alerting in Unified Monitoring, and theming in Charts, Dashboards and Stories.
Detailed release in a box deck